← Back to community benchmarks
kradih--Qwen3.6-27B-MTP-4bit
Performance
1k
tokens
430.1
PP tok/s
18.2
TG tok/s
2381
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.4.4
macOS
macOS 26.5.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 430.1 | 18.2 | 15.8 GB | current |
| 4k | 470.2 | 18.1 | 17.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.2 | 1.00× |
| 2× | 32.8 | 1.80× |